English Text to Speech

Turn English text into natural speech with AI voices. 93 voices. Free, no signup — download as MP3 or WAV.

English text-to-speech spans a wide accent range — General American, Received Pronunciation, Scottish, Irish, Australian, Indian and others — and the choice materially changes vowel quality and rhythm. English is stress-timed, so a natural voice must reduce unstressed syllables to schwa and place sentence stress correctly rather than giving every word equal weight. Its deep orthography (where "ough" reads six different ways) makes a strong pronunciation dictionary and number/abbreviation normalization the hardest part of good English synthesis.

Open the English voice editor

Sample — English

“The quick brown fox jumps over the lazy dog while the morning sun rises slowly above the quiet valley.”

Native name
English
Speakers
1.5 billion total speakers (about 380 million native)
Language family
West Germanic branch of Indo-European
Script
Latin
Spoken in
United States, United Kingdom, Canada, Australia, India, Nigeria, Ireland, New Zealand, South Africa

93 English voices

English Female 1

Bark
Standard Female
Use

English Female 2

Bark
Standard Female
Use

English Female 3

Bark
Standard Female
Use

English Female 4

Bark
Standard Female
Use

English Male 1

Bark
Standard Male
Use

English Male 2

Bark
Standard Male
Use

English Male 3

Bark
Standard Male
Use

English Male 4

Bark
Standard Male
Use

English Male 5

Bark
Standard Male
Use

English Male 6

Bark
Standard Male
Use

English Female 1

Bark Small
Standard Female
Use

English Female 2

Bark Small
Standard Female
Use

English Male 1

Bark Small
Standard Male
Use

Default

Chatterbox
Premium Neutral
Use
Standard Neutral
Use

English Female

CosyVoice 2
Standard Female
Use

English Male

CosyVoice 2
Standard Male
Use

English Female

CosyVoice3
Standard Female
Use

English Male

CosyVoice3
Standard Male
Use

Default

Darwin TTS
Standard Neutral
Use

Speaker 1

Dia TTS
Standard Neutral
Use

Speaker 2

Dia TTS
Standard Neutral
Use

English Default

GPT-SoVITS
Standard Neutral
Use

Default

IndexTTS-2
Standard Neutral
Use
Standard Neutral
Use

Default

Kani TTS 2
Standard Neutral
Use

Bella

Kitten TTS
Free Female
Use

Bruno

Kitten TTS
Free Male
Use

Hugo

Kitten TTS
Free Male
Use

Jasper

Kitten TTS
Free Male
Use

Kiki

Kitten TTS
Free Female
Use
Free Male
Use

Luna

Kitten TTS
Free Female
Use

Rosie

Kitten TTS
Free Female
Use

Adam

Kokoro
Free Male
Use

Bella

Kokoro
Free Female
Use

Emma (British)

Kokoro
Free Female
Use

George (British)

Kokoro
Free Male
Use

Heart

Kokoro
Free Female
Use

Isabella (British)

Kokoro
Free Female
Use

Lewis (British)

Kokoro
Free Male
Use

Michael

Kokoro
Free Male
Use

Nicole

Kokoro
Free Female
Use

Sarah

Kokoro
Free Female
Use

Sky

Kokoro
Free Female
Use

English British

MeloTTS
Free Female
Use

English US

MeloTTS
Free Female
Use

Default

Ming-Omni TTS
Free Neutral
Use

Default

MOSS-TTS Nano
Standard Neutral
Use

Default Speaker

MOSS-TTSD
Standard Neutral
Use

Default

OpenVoice
Premium Neutral
Use

Dan

Orpheus
Standard Male
Use

Jess

Orpheus
Standard Female
Use

Leah

Orpheus
Standard Female
Use

Leo

Orpheus
Standard Male
Use

Mia

Orpheus
Standard Female
Use

Tara

Orpheus
Standard Female
Use

Zac

Orpheus
Standard Male
Use

Zoe

Orpheus
Standard Female
Use

Female 1 (Neutral)

OuteTTS
Free Female
Use

Default

Parler TTS
Standard Neutral
Use

Alan (UK)

Piper
Free Male
Use

Alba (UK)

Piper
Free Female
Use

Amy (US)

Piper
Free Female
Use

Jenny (UK)

Piper
Free Female
Use

Joe (US)

Piper
Free Male
Use

Lessac (US)

Piper
Free Male
Use

Ryan (US)

Piper
Free Male
Use

Alba

Pocket TTS
Free Female
Use

Azelma

Pocket TTS
Free Female
Use

Cosette

Pocket TTS
Free Female
Use

Eponine

Pocket TTS
Free Female
Use

Fantine

Pocket TTS
Free Female
Use

Javert

Pocket TTS
Free Male
Use

Jean

Pocket TTS
Free Male
Use

Marius

Pocket TTS
Free Male
Use

Aiden

Qwen3 TTS
Standard Male
Use

Dylan

Qwen3 TTS
Standard Male
Use

Eric

Qwen3 TTS
Standard Male
Use

Ryan

Qwen3 TTS
Standard Male
Use

Serena

Qwen3 TTS
Standard Female
Use

Vivian

Qwen3 TTS
Standard Female
Use

Speaker 0

Sesame CSM
Premium Neutral
Use

Speaker 1

Sesame CSM
Premium Neutral
Use

Default

Spark TTS
Standard Neutral
Use

Default

StyleTTS 2
Premium Neutral
Use

Random

Tortoise TTS
Premium Neutral
Use

Speaker 1

VibeVoice
Standard Neutral
Use

Speaker 2

VibeVoice
Standard Neutral
Use

Speaker 3

VibeVoice
Standard Neutral
Use

Speaker 4

VibeVoice
Standard Neutral
Use

Default

VITS
Free Neutral
Use

Default

VoxCPM
Standard Neutral
Use

What people use English text to speech for

Audiobook and e-learning narration
YouTube and podcast voiceover
IVR and call-center prompts
Screen readers and accessibility tools
E-commerce and explainer video voiceover

English Text to Speech — FAQ

Voices cover American, British (RP), Australian, Irish, Scottish and Indian English among others, so you can match the accent to your target audience.

Yes. The engine normalizes text first, so "$19.99", "Dr.", "2024" and "St." are expanded to the words a human would actually say in context.

Both are supported. Spellings like "colour/color" or "realise/realize" are read identically; only the selected accent changes how the words sound.

Yes — punctuation drives natural pausing, and supported voices respond to SSML tags for stress, rate and inserted breaks.

Related languages